1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 11:02:59 +02:00
llvm-mirror/lib/IR/LLVMContext.cpp
Yonghong Song 61809186ed [BPF] add new intrinsics preserve_{array,union,struct}_access_index
For background of BPF CO-RE project, please refer to
  http://vger.kernel.org/bpfconf2019.html
In summary, BPF CO-RE intends to compile bpf programs
adjustable on struct/union layout change so the same
program can run on multiple kernels with adjustment
before loading based on native kernel structures.

In order to do this, we need keep track of GEP(getelementptr)
instruction base and result debuginfo types, so we
can adjust on the host based on kernel BTF info.
Capturing such information as an IR optimization is hard
as various optimization may have tweaked GEP and also
union is replaced by structure it is impossible to track
fieldindex for union member accesses.

Three intrinsic functions, preserve_{array,union,struct}_access_index,
are introducted.
  addr = preserve_array_access_index(base, index, dimension)
  addr = preserve_union_access_index(base, di_index)
  addr = preserve_struct_access_index(base, gep_index, di_index)
here,
  base: the base pointer for the array/union/struct access.
  index: the last access index for array, the same for IR/DebugInfo layout.
  dimension: the array dimension.
  gep_index: the access index based on IR layout.
  di_index: the access index based on user/debuginfo types.

For example, for the following example,
  $ cat test.c
  struct sk_buff {
     int i;
     int b1:1;
     int b2:2;
     union {
       struct {
         int o1;
         int o2;
       } o;
       struct {
         char flags;
         char dev_id;
       } dev;
       int netid;
     } u[10];
  };

  static int (*bpf_probe_read)(void *dst, int size, const void *unsafe_ptr)
      = (void *) 4;

  #define _(x) (__builtin_preserve_access_index(x))

  int bpf_prog(struct sk_buff *ctx) {
    char dev_id;
    bpf_probe_read(&dev_id, sizeof(char), _(&ctx->u[5].dev.dev_id));
    return dev_id;
  }
  $ clang -target bpf -O2 -g -emit-llvm -S -mllvm -print-before-all \
    test.c >& log

The generated IR looks like below:

  ...
  define dso_local i32 @bpf_prog(%struct.sk_buff*) #0 !dbg !15 {
    %2 = alloca %struct.sk_buff*, align 8
    %3 = alloca i8, align 1
    store %struct.sk_buff* %0, %struct.sk_buff** %2, align 8, !tbaa !45
    call void @llvm.dbg.declare(metadata %struct.sk_buff** %2, metadata !43, metadata !DIExpression()), !dbg !49
    call void @llvm.lifetime.start.p0i8(i64 1, i8* %3) #4, !dbg !50
    call void @llvm.dbg.declare(metadata i8* %3, metadata !44, metadata !DIExpression()), !dbg !51
    %4 = load i32 (i8*, i32, i8*)*, i32 (i8*, i32, i8*)** @bpf_probe_read, align 8, !dbg !52, !tbaa !45
    %5 = load %struct.sk_buff*, %struct.sk_buff** %2, align 8, !dbg !53, !tbaa !45
    %6 = call [10 x %union.anon]* @llvm.preserve.struct.access.index.p0a10s_union.anons.p0s_struct.sk_buffs(
         %struct.sk_buff* %5, i32 2, i32 3), !dbg !53, !llvm.preserve.access.index !19
    %7 = call %union.anon* @llvm.preserve.array.access.index.p0s_union.anons.p0a10s_union.anons(
         [10 x %union.anon]* %6, i32 1, i32 5), !dbg !53
    %8 = call %union.anon* @llvm.preserve.union.access.index.p0s_union.anons.p0s_union.anons(
         %union.anon* %7, i32 1), !dbg !53, !llvm.preserve.access.index !26
    %9 = bitcast %union.anon* %8 to %struct.anon.0*, !dbg !53
    %10 = call i8* @llvm.preserve.struct.access.index.p0i8.p0s_struct.anon.0s(
         %struct.anon.0* %9, i32 1, i32 1), !dbg !53, !llvm.preserve.access.index !34
    %11 = call i32 %4(i8* %3, i32 1, i8* %10), !dbg !52
    %12 = load i8, i8* %3, align 1, !dbg !54, !tbaa !55
    %13 = sext i8 %12 to i32, !dbg !54
    call void @llvm.lifetime.end.p0i8(i64 1, i8* %3) #4, !dbg !56
    ret i32 %13, !dbg !57
  }

  !19 = distinct !DICompositeType(tag: DW_TAG_structure_type, name: "sk_buff", file: !3, line: 1, size: 704, elements: !20)
  !26 = distinct !DICompositeType(tag: DW_TAG_union_type, scope: !19, file: !3, line: 5, size: 64, elements: !27)
  !34 = distinct !DICompositeType(tag: DW_TAG_structure_type, scope: !26, file: !3, line: 10, size: 16, elements: !35)

Note that @llvm.preserve.{struct,union}.access.index calls have metadata llvm.preserve.access.index
attached to instructions to provide struct/union debuginfo type information.

For &ctx->u[5].dev.dev_id,
  . The "%6 = ..." represents struct member "u" with index 2 for IR layout and index 3 for DI layout.
  . The "%7 = ..." represents array subscript "5".
  . The "%8 = ..." represents union member "dev" with index 1 for DI layout.
  . The "%10 = ..." represents struct member "dev_id" with index 1 for both IR and DI layout.

Basically, traversing the use-def chain recursively for the 3rd argument of bpf_probe_read() and
examining all preserve_*_access_index calls, the debuginfo struct/union/array access index
can be achieved.

The intrinsics also contain enough information to regenerate codes for IR layout.
For array and structure intrinsics, the proper GEP can be constructed.
For union intrinsics, replacing all uses of "addr" with "base" should be enough.

The test case ThinLTO/X86/lazyload_metadata.ll is adjusted to reflect the
new addition of the metadata.

Signed-off-by: Yonghong Song <yhs@fb.com>

Differential Revision: https://reviews.llvm.org/D61810

llvm-svn: 365423
2019-07-09 01:51:36 +00:00

352 lines
11 KiB
C++

//===-- LLVMContext.cpp - Implement LLVMContext ---------------------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file implements LLVMContext, as a wrapper around the opaque
// class LLVMContextImpl.
//
//===----------------------------------------------------------------------===//
#include "llvm/IR/LLVMContext.h"
#include "LLVMContextImpl.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringMap.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/ADT/Twine.h"
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/DiagnosticPrinter.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/RemarkStreamer.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/raw_ostream.h"
#include <cassert>
#include <cstdlib>
#include <string>
#include <utility>
using namespace llvm;
LLVMContext::LLVMContext() : pImpl(new LLVMContextImpl(*this)) {
// Create the fixed metadata kinds. This is done in the same order as the
// MD_* enum values so that they correspond.
std::pair<unsigned, StringRef> MDKinds[] = {
{MD_dbg, "dbg"},
{MD_tbaa, "tbaa"},
{MD_prof, "prof"},
{MD_fpmath, "fpmath"},
{MD_range, "range"},
{MD_tbaa_struct, "tbaa.struct"},
{MD_invariant_load, "invariant.load"},
{MD_alias_scope, "alias.scope"},
{MD_noalias, "noalias"},
{MD_nontemporal, "nontemporal"},
{MD_mem_parallel_loop_access, "llvm.mem.parallel_loop_access"},
{MD_nonnull, "nonnull"},
{MD_dereferenceable, "dereferenceable"},
{MD_dereferenceable_or_null, "dereferenceable_or_null"},
{MD_make_implicit, "make.implicit"},
{MD_unpredictable, "unpredictable"},
{MD_invariant_group, "invariant.group"},
{MD_align, "align"},
{MD_loop, "llvm.loop"},
{MD_type, "type"},
{MD_section_prefix, "section_prefix"},
{MD_absolute_symbol, "absolute_symbol"},
{MD_associated, "associated"},
{MD_callees, "callees"},
{MD_irr_loop, "irr_loop"},
{MD_access_group, "llvm.access.group"},
{MD_callback, "callback"},
{MD_preserve_access_index, "llvm.preserve.access.index"},
};
for (auto &MDKind : MDKinds) {
unsigned ID = getMDKindID(MDKind.second);
assert(ID == MDKind.first && "metadata kind id drifted");
(void)ID;
}
auto *DeoptEntry = pImpl->getOrInsertBundleTag("deopt");
assert(DeoptEntry->second == LLVMContext::OB_deopt &&
"deopt operand bundle id drifted!");
(void)DeoptEntry;
auto *FuncletEntry = pImpl->getOrInsertBundleTag("funclet");
assert(FuncletEntry->second == LLVMContext::OB_funclet &&
"funclet operand bundle id drifted!");
(void)FuncletEntry;
auto *GCTransitionEntry = pImpl->getOrInsertBundleTag("gc-transition");
assert(GCTransitionEntry->second == LLVMContext::OB_gc_transition &&
"gc-transition operand bundle id drifted!");
(void)GCTransitionEntry;
SyncScope::ID SingleThreadSSID =
pImpl->getOrInsertSyncScopeID("singlethread");
assert(SingleThreadSSID == SyncScope::SingleThread &&
"singlethread synchronization scope ID drifted!");
(void)SingleThreadSSID;
SyncScope::ID SystemSSID =
pImpl->getOrInsertSyncScopeID("");
assert(SystemSSID == SyncScope::System &&
"system synchronization scope ID drifted!");
(void)SystemSSID;
}
LLVMContext::~LLVMContext() { delete pImpl; }
void LLVMContext::addModule(Module *M) {
pImpl->OwnedModules.insert(M);
}
void LLVMContext::removeModule(Module *M) {
pImpl->OwnedModules.erase(M);
}
//===----------------------------------------------------------------------===//
// Recoverable Backend Errors
//===----------------------------------------------------------------------===//
void LLVMContext::
setInlineAsmDiagnosticHandler(InlineAsmDiagHandlerTy DiagHandler,
void *DiagContext) {
pImpl->InlineAsmDiagHandler = DiagHandler;
pImpl->InlineAsmDiagContext = DiagContext;
}
/// getInlineAsmDiagnosticHandler - Return the diagnostic handler set by
/// setInlineAsmDiagnosticHandler.
LLVMContext::InlineAsmDiagHandlerTy
LLVMContext::getInlineAsmDiagnosticHandler() const {
return pImpl->InlineAsmDiagHandler;
}
/// getInlineAsmDiagnosticContext - Return the diagnostic context set by
/// setInlineAsmDiagnosticHandler.
void *LLVMContext::getInlineAsmDiagnosticContext() const {
return pImpl->InlineAsmDiagContext;
}
void LLVMContext::setDiagnosticHandlerCallBack(
DiagnosticHandler::DiagnosticHandlerTy DiagnosticHandler,
void *DiagnosticContext, bool RespectFilters) {
pImpl->DiagHandler->DiagHandlerCallback = DiagnosticHandler;
pImpl->DiagHandler->DiagnosticContext = DiagnosticContext;
pImpl->RespectDiagnosticFilters = RespectFilters;
}
void LLVMContext::setDiagnosticHandler(std::unique_ptr<DiagnosticHandler> &&DH,
bool RespectFilters) {
pImpl->DiagHandler = std::move(DH);
pImpl->RespectDiagnosticFilters = RespectFilters;
}
void LLVMContext::setDiagnosticsHotnessRequested(bool Requested) {
pImpl->DiagnosticsHotnessRequested = Requested;
}
bool LLVMContext::getDiagnosticsHotnessRequested() const {
return pImpl->DiagnosticsHotnessRequested;
}
void LLVMContext::setDiagnosticsHotnessThreshold(uint64_t Threshold) {
pImpl->DiagnosticsHotnessThreshold = Threshold;
}
uint64_t LLVMContext::getDiagnosticsHotnessThreshold() const {
return pImpl->DiagnosticsHotnessThreshold;
}
RemarkStreamer *LLVMContext::getRemarkStreamer() {
return pImpl->RemarkDiagStreamer.get();
}
const RemarkStreamer *LLVMContext::getRemarkStreamer() const {
return const_cast<LLVMContext *>(this)->getRemarkStreamer();
}
void LLVMContext::setRemarkStreamer(
std::unique_ptr<RemarkStreamer> RemarkStreamer) {
pImpl->RemarkDiagStreamer = std::move(RemarkStreamer);
}
DiagnosticHandler::DiagnosticHandlerTy
LLVMContext::getDiagnosticHandlerCallBack() const {
return pImpl->DiagHandler->DiagHandlerCallback;
}
void *LLVMContext::getDiagnosticContext() const {
return pImpl->DiagHandler->DiagnosticContext;
}
void LLVMContext::setYieldCallback(YieldCallbackTy Callback, void *OpaqueHandle)
{
pImpl->YieldCallback = Callback;
pImpl->YieldOpaqueHandle = OpaqueHandle;
}
void LLVMContext::yield() {
if (pImpl->YieldCallback)
pImpl->YieldCallback(this, pImpl->YieldOpaqueHandle);
}
void LLVMContext::emitError(const Twine &ErrorStr) {
diagnose(DiagnosticInfoInlineAsm(ErrorStr));
}
void LLVMContext::emitError(const Instruction *I, const Twine &ErrorStr) {
assert (I && "Invalid instruction");
diagnose(DiagnosticInfoInlineAsm(*I, ErrorStr));
}
static bool isDiagnosticEnabled(const DiagnosticInfo &DI) {
// Optimization remarks are selective. They need to check whether the regexp
// pattern, passed via one of the -pass-remarks* flags, matches the name of
// the pass that is emitting the diagnostic. If there is no match, ignore the
// diagnostic and return.
//
// Also noisy remarks are only enabled if we have hotness information to sort
// them.
if (auto *Remark = dyn_cast<DiagnosticInfoOptimizationBase>(&DI))
return Remark->isEnabled() &&
(!Remark->isVerbose() || Remark->getHotness());
return true;
}
const char *
LLVMContext::getDiagnosticMessagePrefix(DiagnosticSeverity Severity) {
switch (Severity) {
case DS_Error:
return "error";
case DS_Warning:
return "warning";
case DS_Remark:
return "remark";
case DS_Note:
return "note";
}
llvm_unreachable("Unknown DiagnosticSeverity");
}
void LLVMContext::diagnose(const DiagnosticInfo &DI) {
if (auto *OptDiagBase = dyn_cast<DiagnosticInfoOptimizationBase>(&DI))
if (RemarkStreamer *RS = getRemarkStreamer())
RS->emit(*OptDiagBase);
// If there is a report handler, use it.
if (pImpl->DiagHandler &&
(!pImpl->RespectDiagnosticFilters || isDiagnosticEnabled(DI)) &&
pImpl->DiagHandler->handleDiagnostics(DI))
return;
if (!isDiagnosticEnabled(DI))
return;
// Otherwise, print the message with a prefix based on the severity.
DiagnosticPrinterRawOStream DP(errs());
errs() << getDiagnosticMessagePrefix(DI.getSeverity()) << ": ";
DI.print(DP);
errs() << "\n";
if (DI.getSeverity() == DS_Error)
exit(1);
}
void LLVMContext::emitError(unsigned LocCookie, const Twine &ErrorStr) {
diagnose(DiagnosticInfoInlineAsm(LocCookie, ErrorStr));
}
//===----------------------------------------------------------------------===//
// Metadata Kind Uniquing
//===----------------------------------------------------------------------===//
/// Return a unique non-zero ID for the specified metadata kind.
unsigned LLVMContext::getMDKindID(StringRef Name) const {
// If this is new, assign it its ID.
return pImpl->CustomMDKindNames.insert(
std::make_pair(
Name, pImpl->CustomMDKindNames.size()))
.first->second;
}
/// getHandlerNames - Populate client-supplied smallvector using custom
/// metadata name and ID.
void LLVMContext::getMDKindNames(SmallVectorImpl<StringRef> &Names) const {
Names.resize(pImpl->CustomMDKindNames.size());
for (StringMap<unsigned>::const_iterator I = pImpl->CustomMDKindNames.begin(),
E = pImpl->CustomMDKindNames.end(); I != E; ++I)
Names[I->second] = I->first();
}
void LLVMContext::getOperandBundleTags(SmallVectorImpl<StringRef> &Tags) const {
pImpl->getOperandBundleTags(Tags);
}
uint32_t LLVMContext::getOperandBundleTagID(StringRef Tag) const {
return pImpl->getOperandBundleTagID(Tag);
}
SyncScope::ID LLVMContext::getOrInsertSyncScopeID(StringRef SSN) {
return pImpl->getOrInsertSyncScopeID(SSN);
}
void LLVMContext::getSyncScopeNames(SmallVectorImpl<StringRef> &SSNs) const {
pImpl->getSyncScopeNames(SSNs);
}
void LLVMContext::setGC(const Function &Fn, std::string GCName) {
auto It = pImpl->GCNames.find(&Fn);
if (It == pImpl->GCNames.end()) {
pImpl->GCNames.insert(std::make_pair(&Fn, std::move(GCName)));
return;
}
It->second = std::move(GCName);
}
const std::string &LLVMContext::getGC(const Function &Fn) {
return pImpl->GCNames[&Fn];
}
void LLVMContext::deleteGC(const Function &Fn) {
pImpl->GCNames.erase(&Fn);
}
bool LLVMContext::shouldDiscardValueNames() const {
return pImpl->DiscardValueNames;
}
bool LLVMContext::isODRUniquingDebugTypes() const { return !!pImpl->DITypeMap; }
void LLVMContext::enableDebugTypeODRUniquing() {
if (pImpl->DITypeMap)
return;
pImpl->DITypeMap.emplace();
}
void LLVMContext::disableDebugTypeODRUniquing() { pImpl->DITypeMap.reset(); }
void LLVMContext::setDiscardValueNames(bool Discard) {
pImpl->DiscardValueNames = Discard;
}
OptPassGate &LLVMContext::getOptPassGate() const {
return pImpl->getOptPassGate();
}
void LLVMContext::setOptPassGate(OptPassGate& OPG) {
pImpl->setOptPassGate(OPG);
}
const DiagnosticHandler *LLVMContext::getDiagHandlerPtr() const {
return pImpl->DiagHandler.get();
}
std::unique_ptr<DiagnosticHandler> LLVMContext::getDiagnosticHandler() {
return std::move(pImpl->DiagHandler);
}